Grok 4.3
Grok 4.3 is a closed AI model from xAI with an index score of 135 (GPT-4 = 100), rank 116 of 217.
135115–156Index score#116 of 217 models
$1.25/ $2.5Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
17 Apr 2026ReleasedReplaced by Grok 4.5
Where it sitson the frontier
o1 reached this score 16 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 10 leaderboards
The Model Indexthird-party tests, our method#116of 217 · 135
LMArena · Creative writingcreative writing#70of 360 · 1422LMArena · Textoverall chat quality, judged by people#81of 362 · 1442LMArena · Codingcoding questions in chat#87of 357 · 1487LMArena · Long promptslong, complex requests#88of 340 · 1443LMArena · Instruction followingfollowing detailed instructions#103of 362 · 1415LMArena · Mathsmaths questions in chat#109of 346 · 1419LMArena · Visionunderstanding images#55of 145 · 1242LMArena · Searchanswering with web search#29of 41 · 1166LMArena · WebDevbuilding web apps and front ends#103of 133 · 1357Best attop three among current models
Replaced by Grok 4.5; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
API providers 1 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released17 Apr 2026
Announcementdocs.x.ai ↗
Release entryGrok 4.3 (beta; API/GA 04-30)
Scored asGrok 4.3
Output speed–
Hugging Faceclosed weights